When Should Teachers Control AI Generation for Mathematics Visuals?

2026-05-11

AI Summary

This study addresses the challenge of effectively integrating teacher control into AI-generated mathematical visualizations to ensure instructional correctness and predictability. It proposes a novel three-stage design space for human-in-the-loop control—pre-generation, during-generation, and post-generation—combining natural language prompting, structured layout confirmation, and object-level editing to enable phased human-AI collaboration. Through a within-subject mixed-methods experiment with 24 elementary mathematics teachers, the research finds that post-generation control yields superior performance in both correctness and predictability. The findings suggest that for educational tasks where accuracy is paramount, systems should blend automation with direct manipulation, aligning teacher intent with staged workflows while balancing perceived agency, predictability, and efficiency.

Abstract

Generative AI has the potential to help teachers rapidly create classroom-ready visual materials, particularly in mathematics where diagrams and visual representations must be pedagogically meaningful and instructionally correct. However, current generative tools primarily support prompting and post-hoc editing, leaving open a key question for correctness-sensitive educational authoring: when in the generation pipeline should teachers exert control? In this paper, we investigate how the timing of human control in AI-assisted generation shapes teachers' visual authoring practices in correctness-sensitive tasks. We introduce a design space of three stages of control: pre-generation control, where users specify intent solely through natural language prompts before generation; mid-generation control, where users inspect and confirm an explicit layout structure before the system completes generation; and post-generation control, where users directly modify AI-generated visuals after generation through object-level edits. In a within-subject, mixed-methods study with 24 primary mathematics teachers, post-generation control received higher ratings on predictability and correctness, while other subjective measures showed no reliable differences. Qualitative findings explain these differences by revealing workflow trade-offs: highly automated, pre-generation control supports rapid ideation but reduces perceived agency and predictability; mid-generation control improves structural alignment at the cost of additional effort; and post-generation control preserves user agency through low-cost, direct verification and correction. Together, these results suggest that in correctness-sensitive educational tasks, effective generative tools should align system behavior with teacher intent and support stage-dependent workflows that combine automation with direct manipulation.

Problem

• generative AI
• teacher control
• mathematics visuals
• correctness-sensitive authoring
• visual generation pipeline

Innovation

• generative AI
• human-AI collaboration
• visual authoring
• control timing
• mathematics education